logo Idiap Research Institute        
 [BibTeX] [Marc21]
Exploiting Contextual Information for Speech/Non-Speech Detection
Type of publication: Conference paper
Citation: Parthasarathi_TSD2008_2008
Booktitle: Text, Speech and Dialogue
Series: Series of Lecture Notes In Artificial Intelligence (LNAI)
Volume: 5246
Year: 2008
Month: 9
Publisher: Springer-Verlag Berlin, Heidelberg
Location: Brno, Czech Republic
ISBN: 978-3-540-87390-7
Crossref: parthasarathi:rr08-22:
Abstract: In this paper, we investigate the effect of temporal context for speech/non-speech detection (SND). It is shown that even a simple feature such as full-band energy, when employed with a large-enough context, shows promise for further investigation. Experimental evaluations on the test data set, with a state-of-the-art multi-layer perceptron based SND system and a simple energy threshold based SND method, using the F-measure, show an absolute performance gain of 4.4% and 5.4% respectively. The optimal contextual length was found to be 1000 ms. Further numerical optimizations yield an improvement (3.37% absolute,',','), resulting in an absolute gain of 7.77% and 8.77% over the MLP based and energy based methods respectively. ROC based performance evaluation also reveals promising performance for the proposed method, particularly in low SNR conditions.
Projects Idiap
Authors Parthasarathi, Sree Hari Krishnan
Motlicek, Petr
Hermansky, Hynek
Added by: [UNK]
Total mark: 0
  • Parthasarathi_TSD2008_2008.pdf